How do I use Gemini 3.5 Flash through YepAPI?

Sign up for a free API key, then send requests to the /v1/ai/chat endpoint.

GoogleText Generation/v1/ai/chat

Gemini 3.5 Flash

Access Gemini 3.5 Flash through one API key. Google's latest fast multimodal model.

Google's latest fast multimodal model. Accepts text, image, audio, and video input, with strong reasoning and a 1M token context window at a low price.

Full Docs Get API Key — Free $5 Credit

No credit card required. Takes 30 seconds.

2,400+

Developers

1.2M+

API calls served

100+

Endpoints

$0.01

Per call

Yep, that's it.

Try it live

Send a message and see Gemini 3.5 Flash respond in real time.

POST/v1/ai/chatgoogle/gemini-3.5-flash

Message *

Max Tokens

Maximum tokens in the response.

Stream

Real-time tokens

Hit "Send Request" to see the response

Context Window

1.0M tokens

Max Output

66K tokens

Input Price

$2.10 / 1M tokens

Output Price

$12.60 / 1M tokens

Strengths

✓

Latest Gemini Flash generation

Google's newest fast model, tuned for low latency and high throughput with strong reasoning, and up to 65,536 output tokens per call — the largest output ceiling in this lineup.

✓

Multimodal input (text, image, audio, video)

Accepts text, images, audio, and video in the same request, enabling transcription, image and document understanding, and video analysis through one model.

✓

1M token context

A 1,048,576-token context window handles long documents, large media inputs, and extended conversations without truncation.

✓

Fast and low-cost

Optimized for speed and price, making it a strong fit for high-volume multimodal and chat workloads where latency and cost matter.

Quick start

Copy this snippet and start making calls with Gemini 3.5 Flash.

const res = await fetch('https://api.yepapi.com/v1/ai/chat', {
  method: 'POST',
  headers: {
    'x-api-key': 'YOUR_API_KEY',
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    "model": "google/gemini-3.5-flash",
    "messages": [
      {
        "role": "user",
        "content": "Explain API gateways in 2 sentences."
      }
    ],
    "maxTokens": 256
  }),
});
const { data } = await res.json();
console.log(data.message.content);

Why use Gemini 3.5 Flash through YepAPI?

✓One API key for all models — no separate accounts

✓OpenAI SDK compatible — just change the base URL

✓No monthly minimums — pay per token

✓Switch models with one line of code

✓Full provider passthrough — citations, search results, and all extras included

✓Streaming and non-streaming support on every model

✓Works with Cursor, Claude, LangChain, and any LLM tool

✓Unified billing across all providers

Gemini 3.5 Flash API — pricing, context window & access

Gemini 3.5 Flash is Google's latest fast multimodal model. It accepts text, image, audio, and video input, reasons well, and pairs a 1M-token context window with an unusually large 65,536-token output ceiling — all at a low price.

YepAPI serves Gemini 3.5 Flash over an OpenAI-compatible endpoint with one API key that also reaches Gemini 3.1 Pro, Claude, Grok, Qwen, Mistral, and Perplexity Sonar, plus SEO, SERP, and scraping APIs.

What is Gemini 3.5 Flash?

Gemini 3.5 Flash is Google's latest speed-optimized model in the Gemini family. It is natively multimodal, accepting text, images, audio, and video in a single request, and it reasons capably while staying fast and inexpensive. With a 1,048,576-token context window and up to 65,536 output tokens, it handles long inputs and produces large outputs. It is positioned as the high-throughput, low-cost option for applications that need multimodal understanding without the latency or price of a Pro-tier model.

Build with Gemini 3.5 Flash via YepAPI

Call Gemini 3.5 Flash through YepAPI's OpenAI-compatible /v1/ai/chat endpoint with the model set to gemini-3.5-flash. Your existing OpenAI SDK code works after changing the base URL and model name. Need deeper reasoning? Swap one string for Gemini 3.1 Pro or Claude; need citations? Switch to Sonar. The same key spans every model, so adding multimodal to a text app is a one-line change.

Gemini 3.5 Flash API pricing — $2.10 / $12.60 per 1M tokens

Gemini 3.5 Flash costs $2.10 per 1M input tokens and $12.60 per 1M output tokens on YepAPI. The low input rate makes it especially cheap for ingestion-heavy multimodal jobs — transcribing audio, captioning images, or analyzing video — where you feed large inputs and return concise results. Billing is per token with no minimums.

Gemini 3.5 Flash for multimodal and high-volume work

Flash is the pick when you need image, audio, or video understanding at scale: document and screenshot parsing, media transcription, video summarization, and fast multimodal chat. Its 1M-token window absorbs large media inputs and its 65K output ceiling supports long structured responses. For high-traffic apps that mix modalities, it offers the best balance of speed and cost in the Gemini line.

Try Gemini 3.5 Flash free

New YepAPI accounts get $5 in free credit with no card required. At Flash's low input rate that covers a meaningful amount of multimodal testing — enough to run images, audio, or video through it before you pay.

Start generating in 30 seconds

$5 free credit on signup. No credit card required. Pay per call.

Get API Key

What developers say

“Switched from SerpAPI and cut our SERP costs by 80%. Same data quality, way simpler billing.”
Marcus T.
SEO Platform Founder

“One API key for AI models, SERP data, and web scraping. Saved us from managing 4 separate providers.”
Priya S.
Full-Stack Developer

“The $5 free credit let us prototype our entire rank tracking feature before committing. No other API does that.”
Jake R.
Indie Hacker

Frequently asked questions

Google's latest fast multimodal model. Accepts text, image, audio, and video input, with strong reasoning and a 1M token context window at a low price.

Input tokens cost $2.10 per 1M tokens and output tokens cost $12.60 per 1M tokens through YepAPI. No monthly minimums — you only pay for what you use.

Gemini 3.5 Flash supports a 1.0M token context window with up to 66K output tokens per request.